From ae38b340dc409f1b9dd66b648eceba09074a2dfd Mon Sep 17 00:00:00 2001
From: MatmaRex <matma.rex@gmail.com>
Date: Mon, 11 Mar 2013 22:24:09 +0100
Subject: [PATCH] IcuCollation::$tailoringFirstLetters: implement letter
 removal
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

This is necessary for Swedish, where 'Þ' ("thorn") - considered a
separate letter by default in the first-letters-root.ser file - is
sorted as 'th', causing unexpected output on category pages - words
starting with 'th'..'u' were placed under a heading with the thorn.

There were three obvious ways to do this:
* somehow include information that this letter is to be removed in the
  string itself, as in 'sv' => array( "Å", "Ä", "Ö", "-Þ" ) - could
  potentially clash with valid uses
* create a separate array other than $tailoringFirstLetters to store
  this information - would cause the data to be fragmented all over
  the file
* include information about letters to be removed in a separate key
  "linked" to the regular one, as in '-sv' => array( "Þ" ) - I see no
  obvious downsides, so this is what I ended up doing

Bug: 45446
Change-Id: I57e07a2027c391c5baa767a68f4409b9de7b4618
---
 includes/Collation.php | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/includes/Collation.php b/includes/Collation.php
index 8a78084ab0..2734871f3d 100644
--- a/includes/Collation.php
+++ b/includes/Collation.php
@@ -181,7 +181,10 @@ class IcuCollation extends Collation {
 
 	/**
 	 * Additional characters (or character groups) to be considered separate
-	 * letters for given languages, compared to the data stored in the
+	 * letters for given languages, or to be removed from the list of such
+	 * letters (denoted by keys starting with '-').
+	 *
+	 * These are additions to (or subtractions from) the data stored in the
 	 * first-letters-root.ser file (which among others includes full basic latin,
 	 * cyrillic and greek alphabets).
 	 *
@@ -262,6 +265,7 @@ class IcuCollation extends Collation {
 		'sq' => array( "Ç", "Dh", "Ë", "Gj", "Ll", "Nj", "Rr", "Sh", "Th", "Xh", "Zh" ),
 		'sr' => array(),
 		'sv' => array( "Å", "Ä", "Ö" ),
+		'-sv' => array( "Þ" ), // sorted as "th" in Swedish, causing unexpected output - bug 45446
 		'tk' => array( "Ç", "Ä", "Ž", "Ň", "Ö", "Ş", "Ü", "Ý" ),
 		'tl' => array( "Ñ", "Ng" ),
 		'tr' => array( "Ç", "Ğ", "İ", "Ö", "Ş", "Ü" ),
@@ -352,7 +356,12 @@ class IcuCollation extends Collation {
 
 		if ( isset ( self::$tailoringFirstLetters[$this->locale] ) ) {
 			$letters = wfGetPrecompiledData( "first-letters-root.ser" );
+			// Append additional characters
 			$letters = array_merge( $letters, self::$tailoringFirstLetters[$this->locale] );
+			// Remove unnecessary ones, if any
+			if ( isset( self::$tailoringFirstLetters[ '-' . $this->locale ] ) ) {
+				$letters = array_diff( $letters, self::$tailoringFirstLetters[ '-' . $this->locale ] );
+			}
 		} else {
 			$letters = wfGetPrecompiledData( "first-letters-{$this->locale}.ser" );
 			if ( $letters === false ) {
-- 
2.20.1